Skip to Content
Building AgentsAgent Builder UI

Agent Builder UI

The Agent Builder is a step-by-step wizard that guides you through creating a new agent.

Accessing the Builder

  1. Navigate to Agents in the sidebar
  2. Click Create Agent

Step 1: Basic Information

┌─────────────────────────────────────────────────────────────────────┐ │ Step 1 of 6: Basic Information │ │ │ │ Name * │ │ [Employee Offboarding Agent ] │ │ │ │ Description │ │ [Handles secure offboarding of departing ] │ │ [employees including access revocation and ] │ │ [knowledge transfer ] │ │ │ │ Project * │ │ [HR Operations ▼] │ │ │ │ [Next →] │ │ │ └─────────────────────────────────────────────────────────────────────┘

Step 2: System Prompt

Define the agent’s behavior and personality:

┌─────────────────────────────────────────────────────────────────────┐ │ Step 2 of 6: System Prompt │ │ │ │ System Prompt * │ │ ┌─────────────────────────────────────────────────────────────┐ │ │ │ You are an HR offboarding specialist. Your responsibilities: │ │ │ │ │ │ │ │ 1. Gather information about the departing employee │ │ │ │ 2. Assess security risk based on access and departure type │ │ │ │ 3. Create a prioritized action plan │ │ │ │ 4. Execute revocations and knowledge transfer │ │ │ │ 5. Generate completion report │ │ │ │ │ │ │ │ Always explain your reasoning. │ │ │ │ Pause for approval on high-risk actions. │ │ │ └─────────────────────────────────────────────────────────────┘ │ │ │ │ 💡 Tip: Be specific about the agent's role and responsibilities │ │ │ │ [← Back] [Next →] │ │ │ └─────────────────────────────────────────────────────────────────────┘

Step 3: Model Configuration

Choose the LLM and parameters:

┌─────────────────────────────────────────────────────────────────────┐ │ Step 3 of 6: Model Configuration │ │ │ │ Model * │ │ [GPT-4 ▼] │ │ │ │ Temperature [0.7 ] │ │ (Higher = more creative, Lower = more consistent) │ │ │ │ Max Tokens per Response [4096 ] │ │ │ │ [← Back] [Next →] │ │ │ └─────────────────────────────────────────────────────────────────────┘

Step 4: Capabilities (Tools)

Select which tools the agent can use:

┌─────────────────────────────────────────────────────────────────────┐ │ Step 4 of 6: Capabilities │ │ │ │ Available Tools Granted Tools │ │ ┌─────────────────────────┐ ┌─────────────────────────┐ │ │ │ □ aws_list_users │ │ ☑ okta_list_user_apps │ │ │ │ □ aws_revoke_access │ → │ ☑ okta_revoke_access │ │ │ │ □ datadog_get_metrics │ ← │ ☑ github_list_repos │ │ │ │ □ jira_create_ticket │ │ ☑ slack_send_message │ │ │ │ □ salesforce_get_account│ │ ☑ memory_read │ │ │ └─────────────────────────┘ │ ☑ memory_write │ │ │ └─────────────────────────┘ │ │ │ │ ⚠ Only grant tools the agent needs │ │ │ │ [← Back] [Next →] │ │ │ └─────────────────────────────────────────────────────────────────────┘

Step 5: Constraints

Set safety limits:

┌─────────────────────────────────────────────────────────────────────┐ │ Step 5 of 6: Constraints │ │ │ │ Maximum Steps [25 ] iterations │ │ Maximum Duration [300 ] seconds │ │ Token Limit [50000 ] tokens │ │ Tool Timeout [30 ] seconds │ │ │ │ Quick Presets: │ │ [Simple Task] [Standard Workflow] [Complex Process] [Custom] │ │ │ │ [← Back] [Next →] │ │ │ └─────────────────────────────────────────────────────────────────────┘

Step 6: Review & Activate

Final review before activation:

┌─────────────────────────────────────────────────────────────────────┐ │ Step 6 of 6: Review & Activate │ │ │ │ Name: Employee Offboarding Agent │ │ Project: HR Operations │ │ Model: GPT-4 (temp: 0.7) │ │ │ │ Capabilities: 6 tools granted │ │ Constraints: 25 steps, 300s timeout, 50K tokens │ │ │ │ ───────────────────────────────────────────────────────────────── │ │ │ │ ○ Save as Draft (edit later) │ │ ● Activate Now (make immutable) │ │ │ │ [← Back] [Create Agent] │ │ │ └─────────────────────────────────────────────────────────────────────┘

After Creation

Once created, you can:

  • Run the agent with test inputs
  • View execution history
  • Create New Version to make changes
  • Configure Triggers for automation